Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    drakeposting meme

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    カップ
    0.43
     dragons
    0.42
    sière
    0.42
     अर्चना
    0.42
     izme
    0.41
     arqu
    0.41
    isio
    0.41
    ısıyla
    0.40
    iscale
    0.40
     zucchero
    0.39
    POSITIVE LOGITS
     ပဲ
    0.42
    ș
    0.41
     Bxc
    0.37
     widening
    0.37
    МО
    0.36
    XE
    0.35
     melap
    0.35
     supervising
    0.35
     반려
    0.34
     دلار
    0.34
    Act Density 0.002%

    No Known Activations